Exploiting Local Indexing and Deep Feature Confidence Scores for Fast Image-To-Video Search

Savas Ozkan, Gözde Bozdağı Akar

Responsive image

Auto-TLDR; Fast and Robust Image-to-Video Retrieval Using Local and Global Descriptors

Slides Poster

Cost-effective visual representation and fast query-by-example search are two challenging goals hat should be provided for web-scale visual retrieval task on a moderate hardware. In this paper, we introduce a fast yet robust method that ensures both of these goals by obtaining the state-of-the-art results for an image-to-video search scenario. To this end, we present important enhancements to commonly used indexing and visual representation techniques by promoting faster, better and more moderate retrieval performance. We also boost the effectiveness of the method for visual distortion by exploiting the individual decision results of local and global descriptors in the query time. By this way, local content descriptors effectively represent copied / duplicated scenes with large geometric deformations, while global descriptors for near duplicate and semantic searches are more practical. Experiments are conducted on the large-scale Stanford I2V dataset. The experimental results show that the method is effective in terms of complexity and query processing time for large-scale visual retrieval scenarios, even if local and global representations are used together. In addition, the proposed method is fairly accurate and achieves state-of-the-art performance based on the mAP score of the dataset. Lastly, we report additional mAP scores after updating the ground annotations obtained by the retrieval results of the proposed method showing more clearly the actual performance.

Similar papers

Hierarchical Deep Hashing for Fast Large Scale Image Retrieval

Yongfei Zhang, Cheng Peng, Zhang Jingtao, Xianglong Liu, Shiliang Pu, Changhuai Chen

Responsive image

Auto-TLDR; Hierarchical indexed deep hashing for fast large scale image retrieval

Slides Poster Similar

Fast image retrieval is of great importance in many computer vision tasks and especially practical applications. Deep hashing, the state-of-the-art fast image retrieval scheme, introduces deep learning to learn the hash functions and generate binary hash codes, and outperforms the other image retrieval methods in terms of accuracy. However, all the existing deep hashing methods could only generate one level hash codes and require a linear traversal of all the hash codes to figure out the closest one when a new query arrives, which is very time-consuming and even intractable for large scale applications. In this work, we propose a Hierarchical Deep HASHing(HDHash) scheme to speed up the state-of-the-art deep hashing methods. More specifically, hierarchical deep hash codes of multiple levels can be generated and indexed with tree structures rather than linear ones, and pruning irrelevant branches can sharply decrease the retrieval time. To our best knowledge, this is the first work to introduce hierarchical indexed deep hashing for fast large scale image retrieval. Extensive experimental results on three benchmark datasets demonstrate that the proposed HDHash scheme achieves better or comparable accuracy with significantly improved efficiency and reduced memory as compared to state-of-the-art fast image retrieval schemes.

Attention-Based Deep Metric Learning for Near-Duplicate Video Retrieval

Kuan-Hsun Wang, Chia Chun Cheng, Yi-Ling Chen, Yale Song, Shang-Hong Lai

Responsive image

Auto-TLDR; Attention-based Deep Metric Learning for Near-duplicate Video Retrieval

Slides Similar

Near-duplicate video retrieval (NDVR) is an important and challenging problem due to the increasing amount of videos uploaded to the Internet. In this paper, we propose an attention-based deep metric learning method for NDVR. Our method is based on well-established principles: We leverage two-stream networks to combine RGB and optical flow features, and incorporate an attention module to effectively deal with distractor frames commonly observed in near duplicate videos. We further aggregate the features corresponding to multiple video segments to enhance the discriminative power. The whole system is trained using a deep metric learning objective with a Siamese architecture. Our experiments show that the attention module helps eliminate redundant and noisy frames, while focusing on visually relevant frames for solving NVDR. We evaluate our approach on recent large-scale NDVR datasets, CC_WEB_VIDEO, VCDB, FIVR and SVD. To demonstrate the generalization ability of our approach, we report results in both within- and cross-dataset settings, and show that the proposed method significantly outperforms state-of-the-art approaches.

Multi-Scale Keypoint Matching

Sina Lotfian, Hassan Foroosh

Responsive image

Auto-TLDR; Multi-Scale Keypoint Matching Using Multi-Scale Information

Slides Poster Similar

We propose a new hierarchical method to match keypoints by exploiting information across multiple scales. Traditionally, for each keypoint a single scale is detected and the matching process is done in the specific scale. We replace this approach with matching across scale-space. The holistic information from higher scales are used for early rejection of candidates that are far away in the feature space. The more localized and finer details of lower scale are then used to decide between remaining possible points. The proposed multi-scale solution is more consistent with the multi-scale processing that is present in the human visual system and is therefore biologically plausible. We evaluate our method on several datasets and achieve state of the art accuracy, while significantly outperforming others in extraction time.

Audio-Based Near-Duplicate Video Retrieval with Audio Similarity Learning

Pavlos Avgoustinakis, Giorgos Kordopatis-Zilos, Symeon Papadopoulos, Andreas L. Symeonidis, Ioannis Kompatsiaris

Responsive image

Auto-TLDR; AuSiL: Audio Similarity Learning for Near-duplicate Video Retrieval

Slides Poster Similar

In this work, we address the problem of audio-based near-duplicate video retrieval. We propose the Audio Similarity Learning (AuSiL) approach that effectively captures temporal patterns of audio similarity between video pairs. For the robust similarity calculation between two videos, we first extract representative audio-based video descriptors by leveraging transfer learning based on a Convolutional Neural Network (CNN) trained on a large scale dataset of audio events, and then we calculate the similarity matrix derived from the pairwise similarity of these descriptors. The similarity matrix is subsequently fed to a CNN network that captures the temporal structures existing within its content. We train our network following a triplet generation process and optimizing the triplet loss function. To evaluate the effectiveness of the proposed approach, we have manually annotated two publicly available video datasets based on the audio duplicity between their videos. The proposed approach achieves very competitive results compared to three state-of-the-art methods. Also, unlike the competing methods, it is very robust for the retrieval of audio duplicates generated with speed transformations.

Visual Localization for Autonomous Driving: Mapping the Accurate Location in the City Maze

Dongfang Liu, Yiming Cui, Xiaolei Guo, Wei Ding, Baijian Yang, Yingjie Chen

Responsive image

Auto-TLDR; Feature Voting for Robust Visual Localization in Urban Settings

Slides Poster Similar

Accurate localization is a foundational capacity, required for autonomous vehicles to accomplish other tasks such as navigation or path planning. It is a common practice for vehicles to use GPS to acquire location information. However, the application of GPS can result in severe challenges when vehicles run within the inner city where different kinds of structures may shadow the GPS signal and lead to inaccurate location results. To address the localization challenges of urban settings, we propose a novel feature voting technique for visual localization. Different from the conventional front-view-based method, our approach employs views from three directions (front, left, and right) and thus significantly improves the robustness of location prediction. In our work, we craft the proposed feature voting method into three state-of-the-art visual localization networks and modify their architectures properly so that they can be applied for vehicular operation. Extensive field test results indicate that our approach can predict location robustly even in challenging inner-city settings. Our research sheds light on using the visual localization approach to help autonomous vehicles to find accurate location information in a city maze, within a desirable time constraint.

Discrete Semantic Matrix Factorization Hashing for Cross-Modal Retrieval

Jianyang Qin, Lunke Fei, Shaohua Teng, Wei Zhang, Genping Zhao, Haoliang Yuan

Responsive image

Auto-TLDR; Discrete Semantic Matrix Factorization Hashing for Cross-Modal Retrieval

Slides Poster Similar

Hashing has been widely studied for cross-modal retrieval due to its promising efficiency and effectiveness in massive data analysis. However, most existing supervised hashing has the limitations of inefficiency for very large-scale search and intractable discrete constraint for hash codes learning. In this paper, we propose a new supervised hashing method, namely, Discrete Semantic Matrix Factorization Hashing (DSMFH), for cross-modal retrieval. First, we conduct the matrix factorization via directly utilizing the available label information to obtain a latent representation, so that both the inter-modality and intra-modality similarities are well preserved. Then, we simultaneously learn the discriminative hash codes and corresponding hash functions by deriving the matrix factorization into a discrete optimization. Finally, we adopt an alternatively iterative procedure to efficiently optimize the matrix factorization and discrete learning. Extensive experimental results on three widely used image-tag databases demonstrate the superiority of the DSMFH over state-of-the-art cross-modal hashing methods.

VSB^2-Net: Visual-Semantic Bi-Branch Network for Zero-Shot Hashing

Xin Li, Xiangfeng Wang, Bo Jin, Wenjie Zhang, Jun Wang, Hongyuan Zha

Responsive image

Auto-TLDR; VSB^2-Net: inductive zero-shot hashing for image retrieval

Slides Poster Similar

Zero-shot hashing aims at learning hashing model from seen classes and the obtained model is capable of generalizing to unseen classes for image retrieval. Inspired by zero-shot learning, existing zero-shot hashing methods usually transfer the supervised knowledge from seen to unseen classes, by embedding the hamming space to a shared semantic space. However, this makes instances difficult to distinguish due to limited hashing bit numbers, especially for semantically similar unseen classes. We propose a novel inductive zero-shot hashing framework, i.e., VSB^2-Net, where both semantic space and visual feature space are embedded to the same hamming space instead. The reconstructive semantic relationships are established in the hamming space, preserving local similarity relationships and explicitly enlarging the discrepancy between semantic hamming vectors. A two-task architecture, comprising of classification module and visual feature reconstruction module, is employed to enhance the generalization and transfer abilities. Extensive evaluation results on several benchmark datasets demonstratethe superiority of our proposed method compared to several state-of-the-art baselines.

Leveraging Quadratic Spherical Mutual Information Hashing for Fast Image Retrieval

Nikolaos Passalis, Anastasios Tefas

Responsive image

Auto-TLDR; Quadratic Mutual Information for Large-Scale Hashing and Information Retrieval

Slides Poster Similar

Several deep supervised hashing techniques have been proposed to allow for querying large image databases. However, it is often overlooked that the process of information retrieval can be modeled using information-theoretic metrics, leading to optimizing various proxies for the problem at hand instead. Contrary to this, we propose a deep supervised hashing algorithm that optimizes the learned codes using an information-theoretic measure, the Quadratic Mutual Information (QMI). The proposed method is adapted to the needs of large-scale hashing and information retrieval leading to a novel information-theoretic measure, the Quadratic Spherical Mutual Information (QSMI), that is inspired by QMI, but leads to significant better retrieval precision. Indeed, the effectiveness of the proposed method is demonstrated under several different scenarios, using different datasets and network architectures, outperforming existing deep supervised image hashing techniques.

Supporting Skin Lesion Diagnosis with Content-Based Image Retrieval

Stefano Allegretti, Federico Bolelli, Federico Pollastri, Sabrina Longhitano, Giovanni Pellacani, Costantino Grana

Responsive image

Auto-TLDR; Skin Images Retrieval Using Convolutional Neural Networks for Skin Lesion Classification and Segmentation

Slides Poster Similar

Given the relevance of skin cancer, many attempts have been dedicated to the creation of automated devices that could assist both expert and beginner dermatologists towards fast and early diagnosis of skin lesions. In recent years, tasks such as skin lesion classification and segmentation have been extensively addressed with deep learning algorithms, which in some cases reach a diagnostic accuracy comparable to that of expert physicians. However, the general lack of interpretability and reliability severely hinders the ability of those approaches to actually support dermatologists in the diagnosis process. In this paper a novel skin images retrieval system is presented, which exploits features extracted by Convolutional Neural Networks to gather similar images from a publicly available dataset, in order to assist the diagnosis process of both expert and novice practitioners. In the proposed framework, Resnet-50 is initially trained for the classification of dermoscopic images; then, the feature extraction part is isolated, and an embedding network is build on top of it. The embedding learns an alternative representation, which allows to check image similarity by means of a distance measure. Experimental results reveal that the proposed method is able to select meaningful images, which can effectively boost the classification accuracy of human dermatologists.

Do We Really Need Scene-Specific Pose Encoders?

Yoli Shavit, Ron Ferens

Responsive image

Auto-TLDR; Pose Regression Using Deep Convolutional Networks for Visual Similarity

Slides Similar

Visual pose regression models estimate the camera pose from a query image with a single forward pass. Current models learn pose encoding from an image using deep convolutional networks which are trained per scene. The resulting encoding is typically passed to a multi-layer perceptron in order to regress the pose. In this work, we propose that scene-specific pose encoders are not required for pose regression and that encodings trained for visual similarity can be used instead. In order to test our hypothesis, we take a shallow architecture of several fully connected layers and train it with pre-computed encodings from a generic image retrieval model. We find that these encodings are not only sufficient to regress the camera pose, but that, when provided to a branching fully connected architecture, a trained model can achieve competitive results and even surpass current state-of-the-art pose regressors in some cases. Moreover, we show that for outdoor localization, the proposed architecture is the only pose regressor, to date, consistently localizing in under 2 meters and 5 degrees.

Improved Deep Classwise Hashing with Centers Similarity Learning for Image Retrieval

Ming Zhang, Hong Yan

Responsive image

Auto-TLDR; Deep Classwise Hashing for Image Retrieval Using Center Similarity Learning

Slides Poster Similar

Deep supervised hashing for image retrieval has attracted researchers' attention due to its high efficiency and superior retrieval performance. Most existing deep supervised hashing works, which are based on pairwise/triplet labels, suffer from the expensive computational cost and insufficient utilization of the semantics information. Recently, deep classwise hashing introduced a classwise loss supervised by class labels information alternatively; however, we find it still has its drawback. In this paper, we propose an improved deep classwise hashing, which enables hashing learning and class centers learning simultaneously. Specifically, we design a two-step strategy on center similarity learning. It interacts with the classwise loss to attract the class center to concentrate on the intra-class samples while pushing other class centers as far as possible. The centers similarity learning contributes to generating more compact and discriminative hashing codes. We conduct experiments on three benchmark datasets. It shows that the proposed method effectively surpasses the original method and outperforms state-of-the-art baselines under various commonly-used evaluation metrics for image retrieval.

Object Classification of Remote Sensing Images Based on Optimized Projection Supervised Discrete Hashing

Qianqian Zhang, Yazhou Liu, Quansen Sun

Responsive image

Auto-TLDR; Optimized Projection Supervised Discrete Hashing for Large-Scale Remote Sensing Image Object Classification

Slides Poster Similar

Recently, with the increasing number of large-scale remote sensing images, the demand for large-scale remote sensing image object classification is growing and attracting the interest of many researchers. Hashing, because of its low memory requirements and high time efficiency, has been widely solve the problem of large-scale remote sensing image. Supervised hashing methods mainly leverage the label information of remote sensing image to learn hash function, however, the similarity of the original feature space cannot be well preserved, which can not meet the accurate requirements for object classification of remote sensing image. To solve the mentioned problem, we propose a novel method named Optimized Projection Supervised Discrete Hashing(OPSDH), which jointly learns a discrete binary codes generation and optimized projection constraint model. It uses an effective optimized projection method to further constraint the supervised hash learning and generated hash codes preserve the similarity based on the data label while retaining the similarity of the original feature space. The experimental results show that OPSDH reaches improved performance compared with the existing hash learning methods and demonstrate that the proposed method is more efficient for operational applications

DFH-GAN: A Deep Face Hashing with Generative Adversarial Network

Bo Xiao, Lanxiang Zhou, Yifei Wang, Qiangfang Xu

Responsive image

Auto-TLDR; Deep Face Hashing with GAN for Face Image Retrieval

Slides Poster Similar

Face Image retrieval is one of the key research directions in computer vision field. Thanks to the rapid development of deep neural network in recent years, deep hashing has achieved good performance in the field of image retrieval. But for large-scale face image retrieval, the performance needs to be further improved. In this paper, we propose Deep Face Hashing with GAN (DFH-GAN), a novel deep hashing method for face image retrieval, which mainly consists of three components: a generator network for generating synthesized images, a discriminator network with a shared CNN to learn multi-domain face feature, and a hash encoding network to generate compact binary hash codes. The generator network is used to perform data augmentation so that the model could learn from both real images and diverse synthesized images. We adopt a two-stage training strategy. In the first stage, the GAN is trained to generate fake images, while in the second stage, to make the network convergence faster. The model inherits the trained shared CNN of discriminator to train the DFH model by using many different supervised loss functions not only in the last layer but also in the middle layer of the network. Extensive experiments on two widely used datasets demonstrate that DFH-GAN can generate high-quality binary hash codes and exceed the performance of the state-of-the-art model greatly.

Hybrid Decomposition Convolution Neural Network and Vocabulary Forest for Image Retrieval

Djenouri Youcef, Jon Hjelmervik

Responsive image

Auto-TLDR; DCNN-vForest: Convolutional Neural Network and Vocabulary Forest for Efficient Image Retrieval

Slides Poster Similar

This paper introduces a highly efficient image retrieval technique called DCNN-vForest (Decomposition Convolution Neural Network and vocabulary Forest), which aims to retrieve the relevant images to the given image query by studying the correlation between images in the image database based on decomposition. The regional and global features of the image database are first extracted using the convolution neural network, and then divided into similar clusters using the Kmeans algorithm. We propose a new structure called vForest (vocabulary Forest), by calculating the vocabulary tree on each cluster of images. The retrieval process benefits from the knowledge provided by the vForest, and instead of considering the whole image database, only the most similar clusters to the image query are explored. To demonstrate the usefulness of our approach, intensive experiments have been carried out on ground-truth image databases, the results reveal the superiority of DCNN-vForest against the baseline image retrieval solutions, in terms of runtime and accuracy.

Comparison of Deep Learning and Hand Crafted Features for Mining Simulation Data

Theodoros Georgiou, Sebastian Schmitt, Thomas Baeck, Nan Pu, Wei Chen, Michael Lew

Responsive image

Auto-TLDR; Automated Data Analysis of Flow Fields in Computational Fluid Dynamics Simulations

Slides Poster Similar

Computational Fluid Dynamics (CFD) simulations are a very important tool for many industrial applications, such as aerodynamic optimization of engineering designs like cars shapes, airplanes parts etc. The output of such simulations, in particular the calculated flow fields, are usually very complex and hard to interpret for realistic three-dimensional real-world applications, especially if time-dependent simulations are investigated. Automated data analysis methods are warranted but a non-trivial obstacle is given by the very large dimensionality of the data. A flow field typically consists of six measurement values for each point of the computational grid in 3D space and time (velocity vector values, turbulent kinetic energy, pressure and viscosity). In this paper we address the task of extracting meaningful results in an automated manner from such high dimensional data sets. We propose deep learning methods which are capable of processing such data and which can be trained to solve relevant tasks on simulation data, i.e. predicting drag and lift forces applied on an airfoil. We also propose an adaptation of the classical hand crafted features known from computer vision to address the same problem and compare a large variety of descriptors and detectors. Finally, we compile a large dataset of 2D simulations of the flow field around airfoils which contains 16000 flow fields with which we tested and compared approaches. Our results show that the deep learning-based methods, as well as hand crafted feature based approaches, are well-capable to accurately describe the content of the CFD simulation output on the proposed dataset.

Cross-Media Hash Retrieval Using Multi-head Attention Network

Zhixin Li, Feng Ling, Chuansheng Xu, Canlong Zhang, Huifang Ma

Responsive image

Auto-TLDR; Unsupervised Cross-Media Hash Retrieval Using Multi-Head Attention Network

Slides Poster Similar

The cross-media hash retrieval method is to encode multimedia data into a common binary hash space, which can effectively measure the correlation between samples from different modalities. In order to further improve the retrieval accuracy, this paper proposes an unsupervised cross-media hash retrieval method based on multi-head attention network. First of all, we use a multi-head attention network to make better matching images and texts, which contains rich semantic information. At the same time, an auxiliary similarity matrix is constructed to integrate the original neighborhood information from different modalities. Therefore, this method can capture the potential correlations between different modalities and within the same modality, so as to make up for the differences between different modalities and within the same modality. Secondly, the method is unsupervised and does not require additional semantic labels, so it has the potential to achieve large-scale cross-media retrieval. In addition, batch normalization and replacement hash code generation functions are adopted to optimize the model, and two loss functions are designed, which make the performance of this method exceed many supervised deep cross-media hash methods. Experiments on three datasets show that the average performance of this method is about 5 to 6 percentage points higher than the state-of-the-art unsupervised method, which proves the effectiveness and superiority of this method.

Fast Discrete Cross-Modal Hashing Based on Label Relaxation and Matrix Factorization

Donglin Zhang, Xiaojun Wu, Zhen Liu, Jun Yu, Josef Kittler

Responsive image

Auto-TLDR; LRMF: Label Relaxation and Discrete Matrix Factorization for Cross-Modal Retrieval

Poster Similar

In recent years, cross-media retrieval has drawn considerable attention due to the exponential growth of multimedia data. Many hashing approaches have been proposed for the cross-media search task. However, there are still open problems that warrant investigation. For example, most existing supervised hashing approaches employ a binary label matrix, which achieves small margins between wrong labels (0) and true labels (1). This may affect the retrieval performance by generating many false negatives and false positives. In addition, some methods adopt a relaxation scheme to solve the binary constraints, which may cause large quantization errors. There are also some discrete hashing methods that have been presented, but most of them are time-consuming. To conquer these problems, we present a label relaxation and discrete matrix factorization method (LRMF) for cross-modal retrieval. It offers a number of innovations. First of all, the proposed approach employs a novel label relaxation scheme to control the margins adaptively, which has the benefit of reducing the quantization error. Second, by virtue of the proposed discrete matrix factorization method designed to learn the binary codes, large quantization errors caused by relaxation can be avoided. The experimental results obtained on two widely-used databases demonstrate that LRMF outperforms state-of-the-art cross-media methods.

Enhancing Deep Semantic Segmentation of RGB-D Data with Entangled Forests

Matteo Terreran, Elia Bonetto, Stefano Ghidoni

Responsive image

Auto-TLDR; FuseNet: A Lighter Deep Learning Model for Semantic Segmentation

Slides Poster Similar

Semantic segmentation is a problem which is getting more and more attention in the computer vision community. Nowadays, deep learning methods represent the state of the art to solve this problem, and the trend is to use deeper networks to get higher performance. The drawback with such models is a higher computational cost, which makes it difficult to integrate them on mobile robot platforms. In this work we want to explore how to obtain lighter deep learning models without compromising performance. To do so we will consider the features used in the Entangled Random Forest algorithm and we will study the best strategies to integrate these within FuseNet deep network. Such new features allow us to shrink the network size without loosing performance, obtaining hence a lighter model which achieves state-of-the-art performance on the semantic segmentation task and represents an interesting alternative for mobile robotics applications, where computational power and energy are limited.

Not 3D Re-ID: Simple Single Stream 2D Convolution for Robust Video Re-Identification

Toby Breckon, Aishah Alsehaim

Responsive image

Auto-TLDR; ResNet50-IBN for Video-based Person Re-Identification using Single Stream 2D Convolution Network

Slides Poster Similar

Video-based person re-identification has received increasing attention recently, as it plays an important role within the surveillance video analysis. Video-based Re-ID is an expansion of earlier image-based re-identification methods by learning features from a video via multiple image frames for each person. Most contemporary video Re-ID methods utilise complex CNN-based network architectures using 3D convolution or multi-branch networks to extract spatial-temporal features from the video. By contrast, in this paper, we will illustrate superior performance from a simple single stream 2D convolution network leveraging the ResNet50-IBN architecture to extract frame-level features followed by temporal attention for clip level features. These clip level features can be generalised to extract video level features by averaging clip level features without any additional cost. Our model, uses best video Re-ID practice and transfer learning between datasets, outperforms existing state-of-the-art approaches on MARS, PRID2011 and iLIDSVID datasets with 89:62%, 97:75%, 97:33% rank-1 accuracy respectively and with 84:61% mAP for MARS, without reliance on complex and memory intensive 3D convolutions or multistream networks architectures as found in other contemporary work. Conversely, this work shows that global features extracted by the 2D convolution network are a sufficient representation for robust state of the art video Re-ID.

Aggregating Object Features Based on Attention Weights for Fine-Grained Image Retrieval

Hongli Lin, Yongqi Song, Zixuan Zeng, Weisheng Wang

Responsive image

Auto-TLDR; DSAW: Unsupervised Dual-selection for Fine-Grained Image Retrieval

Similar

Object localization and local feature representation are key issues in fine-grained image retrieval. However, the existing unsupervised methods still need to be improved in these two aspects. For conquering these issues in a unified framework, a novel unsupervised scheme, named DSAW for short, is presented in this paper. Firstly, we proposed a dual-selection (DS) method, which achieves more accurate object localization by using adaptive threshold method to perform feature selection on local and global activation map in turn. Secondly, a novel and faster self-attention weights (AW) method is developed to weight local features by measuring their importance in the global context. Finally, we also evaluated the performance of the proposed method on five fine-grained image datasets and the results showed that our DSAW outperformed the existing best method.

Rotation Invariant Aerial Image Retrieval with Group Convolutional Metric Learning

Hyunseung Chung, Woo-Jeoung Nam, Seong-Whan Lee

Responsive image

Auto-TLDR; Robust Remote Sensing Image Retrieval Using Group Convolution with Attention Mechanism and Metric Learning

Slides Poster Similar

Remote sensing image retrieval (RSIR) is the process of ranking database images depending on the degree of similarity compared to the query image. As the complexity of RSIR increases due to the diversity in shooting range, angle, and location of remote sensors, there is an increasing demand for methods to address these issues and improve retrieval performance. In this work, we introduce a novel method for retrieving aerial images by merging group convolution with attention mechanism and metric learning, resulting in robustness to rotational variations. For refinement and emphasis on important features, we applied channel attention in each group convolution stage. By utilizing the characteristics of group convolution and channel-wise attention, it is possible to acknowledge the equality among rotated but identically located images. The training procedure has two main steps: (i) training the network with Aerial Image Dataset (AID) for classification, (ii) fine-tuning the network with triplet-loss for retrieval with Google Earth South Korea and NWPU-RESISC45 datasets. Results show that the proposed method performance exceeds other state-of-the-art retrieval methods in both rotated and original environments. Furthermore, we utilize class activation maps (CAM) to visualize the distinct difference of main features between our method and baseline, resulting in better adaptability in rotated environments.

Multi-Level Deep Learning Vehicle Re-Identification Using Ranked-Based Loss Functions

Eleni Kamenou, Jesus Martinez-Del-Rincon, Paul Miller, Patricia Devlin - Hill

Responsive image

Auto-TLDR; Multi-Level Re-identification Network for Vehicle Re-Identification

Slides Poster Similar

Identifying vehicles across a network of cameras with non-overlapping fields of view remains a challenging research problem due to scene occlusions, significant inter-class similarity and intra-class variability. In this paper, we propose an end-to-end multi-level re-identification network that is capable of successfully projecting same identity vehicles closer to one another in the embedding space, compared to vehicles of different identities. Robust feature representations are obtained by combining features at multiple levels of the network. As for the learning process, we employ a recent state-of-the-art structured metric learning loss function previously applied to other retrieval problems and adjust it to the vehicle re-identification task. Furthermore, we explore the cases of image-to-image, image-to-video and video-to-video similarity metric. Finally, we evaluate our system and achieve great performance on two large-scale publicly available datasets, CityFlow-ReID and VeRi-776. Compared to most existing state-of-art approaches, our approach is simpler and more straightforward, utilizing only identity-level annotations, while avoiding post-processing the ranking results (re-ranking) at the testing phase.

A CNN-RNN Framework for Image Annotation from Visual Cues and Social Network Metadata

Tobia Tesan, Pasquale Coscia, Lamberto Ballan

Responsive image

Auto-TLDR; Context-Based Image Annotation with Multiple Semantic Embeddings and Recurrent Neural Networks

Slides Poster Similar

Images represent a commonly used form of visual communication among people. Nevertheless, image classification may be a challenging task when dealing with unclear or non-common images needing more context to be correctly annotated. Metadata accompanying images on social-media represent an ideal source of additional information for retrieving proper neighborhoods easing image annotation task. To this end, we blend visual features extracted from neighbors and their metadata to jointly leverage context and visual cues. Our models use multiple semantic embeddings to achieve the dual objective of being robust to vocabulary changes between train and test sets and decoupling the architecture from the low-level metadata representation. Convolutional and recurrent neural networks (CNNs-RNNs) are jointly adopted to infer similarity among neighbors and query images. We perform comprehensive experiments on the NUS-WIDE dataset showing that our models outperform state-of-the-art architectures based on images and metadata, and decrease both sensory and semantic gaps to better annotate images.

On Identification and Retrieval of Near-Duplicate Biological Images: A New Dataset and Protocol

Thomas E. Koker, Sai Spandana Chintapalli, San Wang, Blake A. Talbot, Daniel Wainstock, Marcelo Cicconet, Mary C. Walsh

Responsive image

Auto-TLDR; BINDER: Bio-Image Near-Duplicate Examples Repository for Image Identification and Retrieval

Poster Similar

Manipulation and re-use of images in scientific publications is a growing issue, not only for biomedical publishers, but also for the research community in general. In this work we introduce BINDER -- Bio-Image Near-Duplicate Examples Repository, a novel dataset to help researchers develop, train, and test models to detect same-source biomedical images. BINDER contains 7,490 unique image patches for model training, 1,821 same-size patch duplicates for validation and testing, and 868 different-size image/patch pairs for image retrieval validation and testing. Except for the training set, patches already contain manipulations including rotation, translation, scale, perspective transform, contrast adjustment and/or compression artifacts. We further use the dataset to demonstrate how novel adaptations of existing image retrieval and metric learning models can be applied to achieve high-accuracy inference results, creating a baseline for future work. In aggregate, we thus present a supervised protocol for near-duplicate image identification and retrieval without any "real-world" training example. Our dataset and source code are available at hms-idac.github.io/BINDER.

Label Self-Adaption Hashing for Image Retrieval

Jianglin Lu, Zhihui Lai, Hailing Wang, Jie Zhou

Responsive image

Auto-TLDR; Label Self-Adaption Hashing for Large-Scale Image Retrieval

Slides Poster Similar

Hashing has attracted widespread attention in image retrieval because of its fast retrieval speed and low storage cost. Compared with supervised methods, unsupervised hashing methods are more reasonable and suitable for large-scale image retrieval since it is always difficult and expensive to collect true labels of the massive data. Without label information, however, unsupervised hashing methods can not guarantee the quality of learned binary codes. To resolve this dilemma, this paper proposes a novel unsupervised hashing method called Label Self-Adaption Hashing (LSAH), which contains effective hashing function learning part and self-adaption label generation part. In the first part, we utilize anchor graph to keep the local structure of the data and introduce joint sparsity into the model to extract effective features for high-quality binary code learning. In the second part, a self-adaptive cluster label matrix is learned from the data under the assumption that the nearest neighbor points should have a large probability to be in the same cluster. Therefore, the proposed LSAH can make full use of the potential discriminative information of the data to guide the learning of binary code. It is worth noting that LSAH can learn effective binary codes, hashing function and cluster labels simultaneously in a unified optimization framework. To solve the resulting optimization problem, an Augmented Lagrange Multiplier based iterative algorithm is elaborately designed. Extensive experiments on three large-scale data sets indicate the promising performance of the proposed LSAH.

RSINet: Rotation-Scale Invariant Network for Online Visual Tracking

Yang Fang, Geunsik Jo, Chang-Hee Lee

Responsive image

Auto-TLDR; RSINet: Rotation-Scale Invariant Network for Adaptive Tracking

Slides Poster Similar

Most Siamese network-based trackers perform the tracking process without model update, and cannot learn target-specific variation adaptively. Moreover, Siamese-based trackers infer the new state of tracked objects by generating axis-aligned bounding boxes, which contain extra background noise, and are unable to accurately estimate the rotation and scale transformation of moving objects, thus potentially reducing tracking performance. In this paper, we propose a novel Rotation-Scale Invariant Network (RSINet) to address the above problem. Our RSINet tracker consists of a target-distractor discrimination branch and a rotation-scale estimation branch, the rotation and scale knowledge can be explicitly learned by a multi-task learning method in an end-to-end manner. In addtion, the tracking model is adaptively optimized and updated under spatio-temporal energy control, which ensures model stability and reliability, as well as high tracking efficiency. Comprehensive experiments on OTB-100, VOT2018, and LaSOT benchmarks demonstrate that our proposed RSINet tracker yields new state-of-the-art performance compared with recent trackers, while running at real-time speed about 45 FPS.

Story Comparison for Estimating Field of View Overlap in a Video Collection

Thierry Malon, Sylvie Chambon, Alain Crouzil, Vincent Charvillat

Responsive image

Auto-TLDR; Finding Videos with Overlapping Fields of View Using Video Data

Slides Similar

Determining the links between large amounts of video data with no prior knowledge of the camera positions is a hard task to automate. From a collection of videos acquired from static cameras simultaneously, we propose a method for finding groups of videos with overlapping fields of view. Each video is first processed individually: at regular time steps, objects are detected and are assigned a category and an appearance descriptor. Next, the video is split into cells at different resolutions and we assign to each cell its story: it consists of the list of objects detected in the cell over time. Once the stories are established for each video, the links between cells of different videos are determined by comparing their stories: two cells are linked if they show simultaneous detections of objects of the same category with similar appearances. Pairs of videos with overlapping fields of view are identified using these links between cells. A link graph is finally returned, in which each node represents a video, and the edges indicate pairs of overlapping videos. The approach is evaluated on a set of 63 real videos from both public datasets and live surveillance videos, as well as on 84 synthetic videos, and shows promising results.

Large-Scale Historical Watermark Recognition: Dataset and a New Consistency-Based Approach

Xi Shen, Ilaria Pastrolin, Oumayma Bounou, Spyros Gidaris, Marc Smith, Olivier Poncet, Mathieu Aubry

Responsive image

Auto-TLDR; Historical Watermark Recognition with Fine-Grained Cross-Domain One-Shot Instance Recognition

Slides Poster Similar

Historical watermark recognition is a highly practical, yet unsolved challenge for archivists and historians. With a large number of well-defined classes, cluttered and noisy samples, different types of representations, both subtle differences between classes and high intra-class variation, historical watermarks are also challenging for pattern recognition. In this paper, overcoming the difficulty of data collection, we present a large public dataset with more than 6k new photographs, allowing for the first time to tackle at scale the scenarios of practical interest for scholars: one-shot instance recognition and cross-domain one-shot instance recognition amongst more than 16k fine-grained classes. We demonstrate that this new dataset is large enough to train modern deep learning approaches, and show that standard methods can be improved considerably by using mid-level deep features. More precisely, we design both a matching score and a feature fine-tuning strategy based on filtering local matches using spatial consistency. This consistency-based approach provides important performance boost compared to strong baselines. Our model achieves 55\% as top-1 accuracy on our very challenging 16,753-class one-shot cross-domain recognition task, each class described by a single drawing from the classic Briquet catalog. In addition to watermark classification, we show our approach provides promising results on fine-grained sketch-based image retrieval.

Localization and Transformation Reconstruction of Image Regions: An Extended Congruent Triangles Approach

Afra'A Ahmad Alyosef, Christian Elias, Andreas Nürnberger

Responsive image

Auto-TLDR; Outlier Filtering of Sub-Image Relations using Geometrical Information

Slides Poster Similar

Most of the existing methods to localize (sub) image relations – a subclass of near-duplicate retrieval techniques – rely on the distinctiveness of matched features of the images being compared. These sets of matching features usually include a proportion of outliers, i.e. features linking non matching regions. In approaches that are designed for retrieval purposes only, these false matches usually have a minor impact on the final ranking. However, if also a localization of regions and corresponding image transformations should be computed, these false matches often have a more significant impact. In this paper, we propose a novel outlier filtering approach based on the geometrical information of the matched features. Our approach is similar to the RANSAC model, but instead of randomly selecting sets of matches and employ them to derive the homography transformation between images or image regions, we exploit in addition the geometrical relation of feature matches to find the best congruent triangle matches. Based on this information we classify outliers and determine the correlation between image regions. We compare our approach with state of art approaches using different feature models and various benchmark data sets (sub-image/panorama with affine transformation, adding blur, noise or scale change). The results indicate that our approach is more robust than the state of art approaches and is able to detect correlation even when most matches are outliers. Moreover, our approach reduces the pre-processing time to filter the matches significantly.

ILS-SUMM: Iterated Local Search for Unsupervised Video Summarization

Yair Shemer, Daniel Rotman, Nahum Shimkin

Responsive image

Auto-TLDR; ILS-SUMM: Iterated Local Search for Video Summarization

Slides Similar

In recent years, there has been an increasing interest in building video summarization tools, where the goal is to automatically create a short summary of an input video that properly represents the original content. We consider shot-based video summarization where the summary consists of a subset of the video shots which can be of various lengths. A straightforward approach to maximize the representativeness of a subset of shots is by minimizing the total distance between shots and their nearest selected shots. We formulate the task of video summarization as an optimization problem with a knapsack-like constraint on the total summary duration. Previous studies have proposed greedy algorithms to solve this problem approximately, but no experiments were presented to measure the ability of these methods to obtain solutions with low total distance. Indeed, our experiments on video summarization datasets show that the success of current methods in obtaining results with low total distance still has much room for improvement. In this paper, we develop ILS-SUMM, a novel video summarization algorithm to solve the subset selection problem under the knapsack constraint. Our algorithm is based on the well-known metaheuristic optimization framework -- Iterated Local Search (ILS), known for its ability to avoid weak local minima and obtain a good near-global minimum. Extensive experiments show that our method finds solutions with significantly better total distance than previous methods. Moreover, to indicate the high scalability of ILS-SUMM, we introduce a new dataset consisting of videos of various lengths.

Weakly Supervised Learning through Rank-Based Contextual Measures

João Gabriel Camacho Presotto, Lucas Pascotti Valem, Nikolas Gomes De Sá, Daniel Carlos Guimaraes Pedronette, Joao Paulo Papa

Responsive image

Auto-TLDR; Exploiting Unlabeled Data for Weakly Supervised Classification of Multimedia Data

Slides Poster Similar

Machine learning approaches have achieved remarkable advances over the last decades, especially in supervised learning tasks such as classification. Meanwhile, multimedia data and applications experienced an explosive growth, becoming ubiquitous in diverse domains. Due to the huge increase in multimedia data collections and the lack of labeled data in several scenarios, creating methods capable of exploiting the unlabeled data and operating under weakly supervision is imperative. In this work, we propose a rank-based model to exploit contextual information encoded in the unlabeled data in order to perform weakly supervised classification. We employ different rank-based correlation measures for identifying strong similarities relationships and expanding the labeled set in an unsupervised way. Subsequently, the extended labeled set is used by a classifier to achieve better accuracy results. The proposed weakly supervised approach was evaluated on multimedia classification tasks, considering several combinations of rank correlation measures and classifiers. An experimental evaluation was conducted on 4 public image datasets and different features. Very positive gains were achieved in comparison with various semi-supervised and supervised classifiers taken as baselines when considering the same amount of labeled data.

Adaptive L2 Regularization in Person Re-Identification

Xingyang Ni, Liang Fang, Heikki Juhani Huttunen

Responsive image

Auto-TLDR; AdaptiveReID: Adaptive L2 Regularization for Person Re-identification

Slides Poster Similar

We introduce an adaptive L2 regularization mechanism termed AdaptiveReID, in the setting of person re-identification. In the literature, it is common practice to utilize hand-picked regularization factors which remain constant throughout the training procedure. Unlike existing approaches, the regularization factors in our proposed method are updated adaptively through backpropagation. This is achieved by incorporating trainable scalar variables as the regularization factors, which are further fed into a scaled hard sigmoid function. Extensive experiments on the Market-1501, DukeMTMC-reID and MSMT17 datasets validate the effectiveness of our framework. Most notably, we obtain state-of-the-art performance on MSMT17, which is the largest dataset for person re-identification. Source code will be published at https://github.com/nixingyang/AdaptiveReID.

Generalized Local Attention Pooling for Deep Metric Learning

Carlos Roig Mari, David Varas, Issey Masuda, Juan Carlos Riveiro, Elisenda Bou-Balust

Responsive image

Auto-TLDR; Generalized Local Attention Pooling for Deep Metric Learning

Slides Poster Similar

Deep metric learning has been key to recent advances in face verification and image retrieval amongst others. These systems consist on a feature extraction block (extracts feature maps from images) followed by a spatial dimensionality reduction block (generates compact image representations from the feature maps) and an embedding generation module (projects the image representation to the embedding space). While research on deep metric learning has focused on improving the losses for the embedding generation module, the dimensionality reduction block has been overlooked. In this work, we propose a novel method to generate compact image representations which uses local spatial information through an attention mechanism, named Generalized Local Attention Pooling (GLAP). This method, instead of being placed at the end layer of the backbone, is connected at an intermediate level, resulting in lower memory requirements. We assess the performance of the aforementioned method by comparing it with multiple dimensionality reduction techniques, demonstrating the importance of using attention weights to generate robust compact image representations. Moreover, we compare the performance of multiple state-of-the-art losses using the standard deep metric learning system against the same experiment with our GLAP. Experiments showcase that the proposed Generalized Local Attention Pooling mechanism outperforms other pooling methods when compared with current state-of-the-art losses for deep metric learning.

Loop-closure detection by LiDAR scan re-identification

Jukka Peltomäki, Xingyang Ni, Jussi Puura, Joni-Kristian Kamarainen, Heikki Juhani Huttunen

Responsive image

Auto-TLDR; Loop-Closing Detection from LiDAR Scans Using Convolutional Neural Networks

Slides Poster Similar

In this work, loop-closure detection from LiDAR scans is defined as an image re-identification problem. Re-identification is performed by computing Euclidean distances of a query scan to a gallery set of previous scans. The distances are computed in a feature embedding space where the scans are mapped by a convolutional neural network (CNN). The network is trained using the triplet loss training strategy. In our experiments we compare different backbone networks, variants of the triplet loss and generic and LiDAR specific data augmentation techniques. With a realistic indoor dataset the best architecture obtains the mean average precision (mAP) above 90%.

Writer Identification Using Deep Neural Networks: Impact of Patch Size and Number of Patches

Akshay Punjabi, José Ramón Prieto Fontcuberta, Enrique Vidal

Responsive image

Auto-TLDR; Writer Recognition Using Deep Neural Networks for Handwritten Text Images

Slides Poster Similar

Traditional approaches for the recognition or identification of the writer of a handwritten text image used to relay on heuristic knowledge about the shape and other features of the strokes of previously segmented characters. However, recent works have done significantly advances on the state of the art thanks to the use of various types of deep neural networks. In most of all of these works, text images are decomposed into patches, which are processed by the networks without any previous character or word segmentation. In this paper, we study how the way images are decomposed into patches impact recognition accuracy, using three publicly available datasets. The study also includes a simpler architecture where no patches are used at all - a single deep neural network inputs a whole text image and directly provides a writer recognition hypothesis. Results show that bigger patches generally lead to improved accuracy, achieving in one of the datasets a significant improvement over the best results reported so far.

Effective Deployment of CNNs for 3DoF Pose Estimation and Grasping in Industrial Settings

Daniele De Gregorio, Riccardo Zanella, Gianluca Palli, Luigi Di Stefano

Responsive image

Auto-TLDR; Automated Deep Learning for Robotic Grasping Applications

Slides Poster Similar

In this paper we investigate how to effectively deploy deep learning in practical industrial settings, such as robotic grasping applications. When a deep-learning based solution is proposed, usually lacks of any simple method to generate the training data. In the industrial field, where automation is the main goal, not bridging this gap is one of the main reasons why deep learning is not as widespread as it is in the academic world. For this reason, in this work we developed a system composed by a 3-DoF Pose Estimator based on Convolutional Neural Networks (CNNs) and an effective procedure to gather massive amounts of training images in the field with minimal human intervention. By automating the labeling stage, we also obtain very robust systems suitable for production-level usage. An open source implementation of our solution is provided, alongside with the dataset used for the experimental evaluation.

Deep Composer: A Hash-Based Duplicative Neural Network for Generating Multi-Instrument Songs

Jacob Galajda, Brandon Royal, Kien Hua

Responsive image

Auto-TLDR; Deep Composer for Intelligence Duplication

Poster Similar

Music is one of the most appreciated forms of art, and generating songs has become a popular subject in the artificial intelligence community. There are various networks that can produce pleasant sounding music, but no model has been able to produce music that duplicates the style of a specific artist or artists. In this paper, we extend a previous single-instrument model: the Deep Composer -a model we believe to be capable of achieving this. Deep Composer originates from the Deep Segment Hash Learning (DSHL) single instrument model and is designed to learn how a specific artist would place individual segments of music together rather than create music similar to a specific genre. To the best of our knowledge, no other network has been designed to achieve this. For these reasons, we introduce a new field of study, Intelligence Duplication (ID). AI research generally focuses on developing techniques to mimic universal intelligence. Intelligence Duplication (ID) research focuses on techniques to artificially duplicate or clone a specific mind such as Mozart. Additionally, we present a new retrieval algorithm, Segment Barrier Retrieval (SBR), to improve retrieval accuracy within the hash-space as opposed to a more traditionally used feature-space. SBR prevents retrieval branches from entering areas of low-density within the hash-space, a phenomena we identify and label as segment sparsity. To test our Deep Composer and the effectiveness of SBR, we evaluate various models with different SBR threshold values and conduct qualitative surveys for each model. The survey results indicate that our Deep Composer model is capable of learning music generation from multiple composers. Our extended Deep Composer model provides a more suitable platform for Intelligence Duplication. Future work can apply this platform to duplicate great composers such as Mozart or allow them to collaborate in the virtual space.

Distinctive 3D Local Deep Descriptors

Fabio Poiesi, Davide Boscaini

Responsive image

Auto-TLDR; DIPs: Local Deep Descriptors for Point Cloud Regression

Slides Poster Similar

We present a simple but yet effective method for learning distinctive 3D local deep descriptors (DIPs) that can be used to register point clouds without requiring an initial alignment. Point cloud patches are extracted, canonicalised with respect to their estimated local reference frame and encoded into rotation-invariant compact descriptors by a PointNet-based deep neural network. DIPs can effectively generalise across different sensor modalities because they are learnt end-to-end from locally and randomly sampled points. Moreover, because DIPs encode only local geometric information, they are robust to clutter, occlusions and missing regions. We evaluate and compare DIPs against alternative hand-crafted and deep descriptors on several indoor and outdoor datasets reconstructed using different sensors. Results show that DIPs (i) achieve comparable results to the state-of-the-art on RGB-D indoor scenes (3DMatch dataset), (ii) outperform state-of-the-art by a large margin on laser-scanner outdoor scenes (ETH dataset), and (iii) generalise to indoor scenes reconstructed with the Visual-SLAM system of Android ARCore.

A Grid-Based Representation for Human Action Recognition

Soufiane Lamghari, Guillaume-Alexandre Bilodeau, Nicolas Saunier

Responsive image

Auto-TLDR; GRAR: Grid-based Representation for Action Recognition in Videos

Slides Poster Similar

Human action recognition (HAR) in videos is a fundamental research topic in computer vision. It consists mainly in understanding actions performed by humans based on a sequence of visual observations. In recent years, HAR have witnessed significant progress, especially with the emergence of deep learning models. However, most of existing approaches for action recognition rely on information that is not always relevant for the task, and are limited in the way they fuse temporal information. In this paper, we propose a novel method for human action recognition that encodes efficiently the most discriminative appearance information of an action with explicit attention on representative pose features, into a new compact grid representation. Our GRAR (Grid-based Representation for Action Recognition) method is tested on several benchmark datasets that demonstrate that our model can accurately recognize human actions, despite intra-class appearance variations and occlusion challenges.

Ordinal Depth Classification Using Region-Based Self-Attention

Minh Hieu Phan, Son Lam Phung, Abdesselam Bouzerdoum

Responsive image

Auto-TLDR; Region-based Self-Attention for Multi-scale Depth Estimation from a Single 2D Image

Slides Poster Similar

Depth estimation from a single 2D image has been widely applied in 3D understanding, 3D modelling and robotics. It is challenging as reliable cues (e.g. stereo correspondences and motions) are not available. Most of the modern approaches exploited multi-scale feature extraction to provide more powerful representations for deep networks. However, these studies have not focused on how to effectively fuse the learned multi-scale features. This paper proposes a novel region-based self-attention (rSA) module. The rSA recalibrates the multi-scale responses by explicitly modelling the interdependency between channels in separate image regions. We discretize continuous depths to solve an ordinal depth classification in which the relative order between categories is significant. We contribute a dataset of 4410 RGB-D images, captured in outdoor environments at the University of Wollongong's campus. In our experimental results, the proposed module improves the lightweight models on small-sized datasets by 22% - 40%

Progressive Learning Algorithm for Efficient Person Re-Identification

Zhen Li, Hanyang Shao, Liang Niu, Nian Xue

Responsive image

Auto-TLDR; Progressive Learning Algorithm for Large-Scale Person Re-Identification

Slides Poster Similar

This paper studies the problem of Person Re-Identification (ReID) for large-scale applications. Recent research efforts have been devoted to building complicated part models, which introduce considerably high computational cost and memory consumption, inhibiting its practicability in large-scale applications. This paper aims to develop a novel learning strategy to find efficient feature embeddings while maintaining the balance of accuracy and model complexity. More specifically, we find by enhancing the classical triplet loss together with cross-entropy loss, our method can explore the hard examples and build a discriminant feature embedding yet compact enough for large-scale applications. Our method is carried out progressively using Bayesian optimization, and we call it the Progressive Learning Algorithm (PLA). Extensive experiments on three large-scale datasets show that our PLA is comparable or better than the state-of-the-arts. Especially, on the challenging Market-1501 dataset, we achieve Rank-1=94.7\%/mAP=89.4\% while saving at least 30\% parameters than strong part models.

Joint Learning Multiple Curvature Descriptor for 3D Palmprint Recognition

Lunke Fei, Bob Zhang, Jie Wen, Chunwei Tian, Peng Liu, Shuping Zhao

Responsive image

Auto-TLDR; Joint Feature Learning for 3D palmprint recognition using curvature data vectors

Slides Poster Similar

3D palmprint-based biometric recognition has drawn growing research attention due to its several merits over 2D counterpart such as robust structural measurement of a palm surface and high anti-counterfeiting capability. However, most existing 3D palmprint descriptors are hand-crafted that usually extract stationary features from 3D palmprint images. In this paper, we propose a feature learning method to jointly learn compact curvature feature descriptor for 3D palmprint recognition. We first form multiple curvature data vectors to completely sample the intrinsic curvature information of 3D palmprint images. Then, we jointly learn a feature projection function that project curvature data vectors into binary feature codes, which have the maximum inter-class variances and minimum intra-class distance so that they are discriminative. Moreover, we learn the collaborative binary representation of the multiple curvature feature codes by minimizing the information loss between the final representation and the multiple curvature features, so that the proposed method is more compact in feature representation and efficient in matching. Experimental results on the baseline 3D palmprint database demonstrate the superiority of the proposed method in terms of recognition performance in comparison with state-of-the-art 3D palmprint descriptors.

Light3DPose: Real-Time Multi-Person 3D Pose Estimation from Multiple Views

Alessio Elmi, Davide Mazzini, Pietro Tortella

Responsive image

Auto-TLDR; 3D Pose Estimation of Multiple People from a Few calibrated Camera Views using Deep Learning

Slides Poster Similar

We present an approach to perform 3D pose estimation of multiple people from a few calibrated camera views. Our architecture, leveraging the recently proposed unprojection layer, aggregates feature-maps from a 2D pose estimator backbone into a comprehensive representation of the 3D scene. Such intermediate representation is then elaborated by a fully-convolutional volumetric network and a decoding stage to extract 3D skeletons with sub-voxel accuracy. Our method achieves state of the art MPJPE on the CMU Panoptic dataset using a few unseen views and obtains competitive results even with a single input view. We also assess the transfer learning capabilities of the model by testing it against the publicly available Shelf dataset obtaining good performance metrics. The proposed method is inherently efficient: as a pure bottom-up approach, it is computationally independent of the number of people in the scene. Furthermore, even though the computational burden of the 2D part scales linearly with the number of input views, the overall architecture is able to exploit a very lightweight 2D backbone which is orders of magnitude faster than the volumetric counterpart, resulting in fast inference time. The system can run at 6 FPS, processing up to 10 camera views on a single 1080Ti GPU.

Text Synopsis Generation for Egocentric Videos

Aidean Sharghi, Niels Lobo, Mubarak Shah

Responsive image

Auto-TLDR; Egocentric Video Summarization Using Multi-task Learning for End-to-End Learning

Slides Similar

Mass utilization of body-worn cameras has led to a huge corpus of available egocentric video. Existing video summarization algorithms can accelerate browsing such videos by selecting (visually) interesting shots from them. Nonetheless, since the system user still has to watch the summary videos, browsing large video databases remain a challenge. Hence, in this work, we propose to generate a textual synopsis, consisting of a few sentences describing the most important events in a long egocentric videos. Users can read the short text to gain insight about the video, and more importantly, efficiently search through the content of a large video database using text queries. Since egocentric videos are long and contain many activities and events, using video-to-text algorithms results in thousands of descriptions, many of which are incorrect. Therefore, we propose a multi-task learning scheme to simultaneously generate descriptions for video segments and summarize the resulting descriptions in an end-to-end fashion. We Input a set of video shots and the network generates a text description for each shot. Next, visual-language content matching unit that is trained with a weakly supervised objective, identifies the correct descriptions. Finally, the last component of our network, called purport network, evaluates the descriptions all together to select the ones containing crucial information. Out of thousands of descriptions generated for the video, a few informative sentences are returned to the user. We validate our framework on the challenging UT Egocentric video dataset, where each video is between 3 to 5 hours long, associated with over 3000 textual descriptions on average. The generated textual summaries, including only 5 percent (or less) of the generated descriptions, are compared to groundtruth summaries in text domain using well-established metrics in natural language processing.

Equation Attention Relationship Network (EARN) : A Geometric Deep Metric Framework for Learning Similar Math Expression Embedding

Saleem Ahmed, Kenny Davila, Srirangaraj Setlur, Venu Govindaraju

Responsive image

Auto-TLDR; Representational Learning for Similarity Based Retrieval of Mathematical Expressions

Slides Poster Similar

Representational Learning in the form of high dimensional embeddings have been used for multiple pattern recognition applications. There has been a significant interest in building embedding based systems for learning representationsin the mathematical domain. At the same time, retrieval of structured information such as mathematical expressions is an important need for modern IR systems. In this work, our motivation is to introduce a robust framework for learning representations for similarity based retrieval of mathematical expressions. Given a query by example, the embedding can find the closest matching expression as a function of euclidean distance between them. We leverage recent advancements in image-based and graph-based deep learning algorithms to learn our similarity embeddings. We do this first, by using uni-modal encoders in graph space and image space and then, a multi-modal combination of the same. To overcome the lack of training data, we force the networks to learn a deep metric using triplets generated with a heuristic scoring function. We also adopt a custom strategy for mining hard samples to train our neural networks. Our system produces rankings similar to those generated by the original scoring function, but using only a fraction of the time. Our results establish the viability of using such a multi-modal embedding for this task.

RISEdb: A Novel Indoor Localization Dataset

Carlos Sanchez Belenguer, Erik Wolfart, Álvaro Casado Coscollá, Vitor Sequeira

Responsive image

Auto-TLDR; Indoor Localization Using LiDAR SLAM and Smartphones: A Benchmarking Dataset

Slides Poster Similar

In this paper we introduce a novel public dataset for developing and benchmarking indoor localization systems. We have selected and 3D mapped a set of representative indoor environments including a large office building, a conference room, a workshop, an exhibition area and a restaurant. Our acquisition pipeline is based on a portable LiDAR SLAM backpack to map the buildings and to accurately track the pose of the user as it moves freely inside them. We introduce the calibration procedures that enable us to acquire and geo-reference live data coming from different independent sensors rigidly attached to the backpack. This has allowed us to collect long sequences of spherical and stereo images, together with all the sensor readings coming from a consumer smartphone and locate them inside the map with centimetre accuracy. The dataset addresses many of the limitations of existing indoor localization datasets regarding the scale and diversity of the mapped buildings; the number of acquired sequences under varying conditions; the accuracy of the ground-truth trajectory; the availability of a detailed 3D model and the availability of different sensor types. It enables the benchmarking of existing and the development of new indoor localization approaches, in particular for deep learning based systems that require large amounts of labeled training data.

Modeling the Distribution of Normal Data in Pre-Trained Deep Features for Anomaly Detection

Oliver Rippel, Patrick Mertens, Dorit Merhof

Responsive image

Auto-TLDR; Deep Feature Representations for Anomaly Detection in Images

Slides Poster Similar

Anomaly Detection (AD) in images is a fundamental computer vision problem and refers to identifying images and/or image substructures that deviate significantly from the norm. Popular AD algorithms commonly try to learn a model of normality from scratch using task specific datasets, but are limited to semi-supervised approaches employing mostly normal data due to the inaccessibility of anomalies on a large scale combined with the ambiguous nature of anomaly appearance. We follow an alternative approach and demonstrate that deep feature representations learned by discriminative models on large natural image datasets are well suited to describe normality and detect even subtle anomalies. Our model of normality is established by fitting a multivariate Gaussian to deep feature representations of classification networks trained on ImageNet using normal data only in a transfer learning setting. By subsequently applying the Mahalanobis distance as the anomaly score we outperform the current state of the art on the public MVTec AD dataset, achieving an Area Under the Receiver Operating Characteristic curve of 95.8 +- 1.2 % (mean +- SEM) over all 15 classes. We further investigate why the learned representations are discriminative to the AD task using Principal Component Analysis. We find that the principal components containing little variance in normal data are the ones crucial for discriminating between normal and anomalous instances. This gives a possible explanation to the often sub-par performance of AD approaches trained from scratch using normal data only. By selectively fitting a multivariate Gaussian to these most relevant components only, we are able to further reduce model complexity while retaining AD performance. We also investigate setting the working point by selecting acceptable False Positive Rate thresholds based on the multivariate Gaussian assumption.

Can You Trust Your Pose? Confidence Estimation in Visual Localization

Luca Ferranti, Xiaotian Li, Jani Boutellier, Juho Kannala

Responsive image

Auto-TLDR; Pose Confidence Estimation in Large-Scale Environments: A Light-weight Approach to Improving Pose Estimation Pipeline

Slides Poster Similar

Camera pose estimation in large-scale environments is still an open question and, despite recent promising results, it may still fail in some situations. The research so far has focused on improving subcomponents of estimation pipelines, to achieve more accurate poses. However, there is no guarantee for the result to be correct, even though the correctness of pose estimation is critically important in several visual localization applications, such as in autonomous navigation. In this paper we bring to attention a novel research question, pose confidence estimation, where we aim at quantifying how reliable the visually estimated pose is. We develop a novel confidence measure to fulfill this task and show that it can be flexibly applied to different datasets, indoor or outdoor, and for various visual localization pipelines. We also show that the proposed techniques can be used to accomplish a secondary goal: improving the accuracy of existing pose estimation pipelines. Finally, the proposed approach is computationally light-weight and adds only a negligible increase to the computational effort of pose estimation.